Research Scientist, Real-Time Video Generation

Cantina

. Develop real-time and streaming generation models for responsive interaction while maintaining visual quality and consistency over time .

Posted 10/27/2026full-timeRemoteMid-LevelSeniorWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in developing and fine-tuning generative video models, with a focus on improving interaction quality and efficiency. Capable of conducting thorough evaluations and adapting methodologies based on experimental findings.

Highest-signal resume keywords

Generative Model TrainingVideo Model Fine-TuningExperimental JudgmentClear CommunicationModel Evaluation

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

Real-Time Model DevelopmentStreaming Generation ModelsLatency InvestigationData CurationModel Behavior AnalysisQuantitative EvaluationsQualitative EvaluationsSpeech and Motion Relationship ImprovementTraining Objective InvestigationRuntime Improvement Techniques

Soft Skills

OwnershipClear CommunicationQuick Learning

Industry Keywords

Video GenerationModel DistillationBehavior AdaptationData CoverageSampling Improvement

About the role

Key responsibilities & impact

Develop real-time and streaming generation models for responsive interaction while maintaining visual quality and consistency over time
Investigate latency, continuity, and model behavior during longer generation
Explore character appearance, facial expression, gesture, and body movement
Improve the relationship between speech and motion across identities and visual styles
Adapt video models to new data, behaviors, and capabilities through fine-tuning and post-training
Investigate training objectives and conditioning methods and follow ideas through implementation and evaluation
Improve generation speed and efficiency through distillation, model-level approaches, and runtime improvements
Measure quality, latency, and memory effects
Identify missing data coverage and recurring failure modes; improve curation and sampling
Develop data that helps models learn desired behavior
Build quantitative and qualitative evaluations of generated video and interaction experience
Read, reproduce, and adapt relevant research
Share experiments, demos, and findings
Help the team prioritize research directions, time, and compute

Requirements

What you’ll need

Experience training or fine-tuning video or related generative models
Ability to learn unfamiliar methods quickly and turn ideas into useful experiments
Good experimental judgment, ownership, and clear communication

Benefits

Comp & perks

Generous company equity
Medical, dental, and vision insurance – 99.99% of premiums covered by Cantina
42 days of paid time off, including 15 PTO days, 10 sick days, 15 company holidays, and 2 floating holidays
Generous parental leave & fertility support
401(k) retirement savings plan
Lifestyle spending account – $500/month to use however you’d like
Complimentary lunch and snacks for in-office employees
One Medical membership
Benefits listed for U.S.-based roles